add_representation · Vmd MCP: Risk & Policy

WHAT IT DOES

What add_representation does on Vmd

AI agents use add_representation to create or update resources in Vmd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vmd environment.

WHY IT NEEDS A POLICY

Why add_representation needs a policy

The tool adds configuration/metadata to an existing molecule (a new representation), which is a reversible modification. It does not delete, execute arbitrary commands, or have financial impact. While VMD2 is scientific software, the blast radius of misuse is limited to the visualization layer—a user could add unwanted representations, but this is easily undone via delete_representation.

From the tool's definition Tool creates a new visual representation in VMD2 ('Add a new visual representation'). This modifies the state of the molecular visualization without removing or deleting existing data, consistent with reversible Write operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_representation Rate-limited

add_representation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_representation": {
      "limits": [
        {
          "counter": "add_representation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Vmd, so you can run agents against it safely.

FAQ

Questions about add_representation

What does the add_representation tool do? +

Add a new visual representation to a molecule WITHOUT removing existing ones. It is categorised as a Write tool in the Vmd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_representation? +

Register the Vmd MCP server in PolicyLayer and add a rule for add_representation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vmd. Nothing to install.

What risk level is add_representation? +

add_representation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_representation? +

Yes. Add a rate_limit block to the add_representation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block add_representation completely? +

Set action: deny in the PolicyLayer policy for add_representation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides add_representation? +

add_representation is provided by the Vmd MCP server (omararias-gaguancela/vmd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.